Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/openWorld/non-destructive, but the description goes further: long judgments are paged, responses may return ok=false with a fallback hint when SAOS is unavailable or rate-limited, and the correct recovery is an out-of-band fetch of saos_url. This is exactly the failure-mode and rate-limit context annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the one-line purpose, then the precondition, then paging, then the failure path — each sentence adds distinct operational value with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value documentation is unnecessary; the description covers the invocation prerequisite, pagination loop, and degraded-mode behavior. An agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry all three params. It clarifies offset semantics indirectly ('call again with offset=next_offset') and hints at max_chars via 'bounded text excerpt', but never defines saos_id's meaning and leaves max_chars' unit/default behavior to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Fetch one SAOS court judgment') plus the payload shape ('metadata + bounded text excerpt'). It is immediately distinguishable from siblings like related_cases, research_cases, and search_case_by_signature, which are named as ID sources rather than as alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit precondition: 'Use only with a saos_id returned by related_cases, research_cases, or search_case_by_signature.' It also states the when-not case — do not retry on rate-limiting/unavailability, fetch saos_url instead — and gives the paging procedure with has_more/next_offset.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.